Machine Learning-based Beamforming Design for Millimeter Wave IRS Communications with Discrete Phase Shifters

TL;DR

This paper introduces a machine learning-based algorithm for joint active and passive beamforming in millimeter-wave IRS-assisted systems, achieving near-optimal power minimization with reduced complexity.

Contribution

It proposes a novel low-complexity cross-entropy algorithm for joint beamforming optimization in IRS-assisted millimeter-wave communications, extending to high-resolution phase shifts.

Findings

The algorithm achieves near-optimal solutions.

It reduces computational complexity compared to existing methods.

Extends phase shift resolution to improve performance.

Abstract

In this paper, we investigate an intelligent reflecting surface (IRS)-assisted millimeter-wave multiple-input single-output downlink wireless communication system. By jointly calculating the active beamforming at the base station and the passive beamforming at the IRS, we aim to minimize the transmit power under the constraint of each user' signal-to-interference-plus-noise ratio. To solve this problem, we propose a low-complexity machine learning-based cross-entropy (CE) algorithm to alternately optimize the active beamforming and the passive beamforming. Specifically, in the alternative iteration process, the zero-forcing (ZF) method and CE algorithm are applied to acquire the active beamforming and the passive beamforming, respectively. The CE algorithm starts with random sampling, by the idea of distribution focusing, namely shifting the distribution towards a desired one by minimizing CE, and a near optimal reflection coefficients with adequately high probability can be obtained. In addition, we extend the original one-bit phase shift at the IRS to the common case with high-resolution phase shift to enhance the effectiveness of the algorithms. Simulation results verify that the proposed algorithm can obtain a near optimal solution with lower computational complexity.